Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data

Zhen Hu; Gyorgy J. Simon; Elliot G. Arsoniadis; Yan Wang; Mary R. Kwaan; Genevieve B. Melton

doi:10.3233/978-1-61499-564-7-706

Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data

Zhen Hu, Gyorgy J. Simon, Elliot G. Arsoniadis, Yan Wang, Mary R. Kwaan, Genevieve B. Melton

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

43 Scopus citations

Abstract

The National Surgical Quality Improvement Project (NSQIP) is widely recognized as 'the best in the nation' surgical quality improvement resource in the United States. In particular, it rigorously defines postoperative morbidity outcomes, including surgical adverse events occurring within 30 days of surgery. Due to its manual yet expensive construction process, the NSQIP registry is of exceptionally high quality, but its high cost remains a significant bottleneck to NSQIP's wider dissemination. In this work, we propose an automated surgical adverse events detection tool, aimed at accelerating the process of extracting postoperative outcomes from medical charts. As a prototype system, we combined local EHR data with the NSQIP gold standard outcomes and developed machine learned models to retrospectively detect Surgical Site Infections (SSI), a particular family of adverse events that NSQIP extracts. The built models have high specificity (from 0.788 to 0.988) as well as very high negative predictive values (>0.98), reliably eliminating the vast majority of patients without SSI, thereby significantly reducing the NSQIP extractors' burden.

Original language	English (US)
Title of host publication	MEDINFO 2015
Subtitle of host publication	eHealth-Enabled Health - Proceedings of the 15th World Congress on Health and Biomedical Informatics
Editors	Andrew Georgiou, Indra Neil Sarkar, Paulo Mazzoncini de Azevedo Marques
Publisher	IOS Press
Pages	706-710
Number of pages	5
ISBN (Electronic)	9781614995630
DOIs	https://doi.org/10.3233/978-1-61499-564-7-706
State	Published - 2015
Event	15th World Congress on Health and Biomedical Informatics, MEDINFO 2015 - Sao Paulo, Brazil Duration: Aug 19 2015 → Aug 23 2015

Publication series

Name	Studies in Health Technology and Informatics
Volume	216
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Other

Other	15th World Congress on Health and Biomedical Informatics, MEDINFO 2015
Country/Territory	Brazil
City	Sao Paulo
Period	8/19/15 → 8/23/15

Bibliographical note

Publisher Copyright:
© 2015 IMIA and IOS Press.

Keywords

Electronic Health Records
National Surgical Quality Improvement Project
Supervised Learning
Surgical Site Infection

Publisher link

10.3233/978-1-61499-564-7-706

Find It

Find It at U of M Libraries

Cite this

Hu, Z., Simon, G. J., Arsoniadis, E. G., Wang, Y., Kwaan, M. R., & Melton, G. B. (2015). Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data. In A. Georgiou, I. N. Sarkar, & P. M. de Azevedo Marques (Eds.), MEDINFO 2015: eHealth-Enabled Health - Proceedings of the 15th World Congress on Health and Biomedical Informatics (pp. 706-710). (Studies in Health Technology and Informatics; Vol. 216). IOS Press. https://doi.org/10.3233/978-1-61499-564-7-706

Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data. / Hu, Zhen; Simon, Gyorgy J.; Arsoniadis, Elliot G. et al.
MEDINFO 2015: eHealth-Enabled Health - Proceedings of the 15th World Congress on Health and Biomedical Informatics. ed. / Andrew Georgiou; Indra Neil Sarkar; Paulo Mazzoncini de Azevedo Marques. IOS Press, 2015. p. 706-710 (Studies in Health Technology and Informatics; Vol. 216).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hu, Z, Simon, GJ , Arsoniadis, EG, Wang, Y, Kwaan, MR & Melton, GB 2015, Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data. in A Georgiou, IN Sarkar & PM de Azevedo Marques (eds), MEDINFO 2015: eHealth-Enabled Health - Proceedings of the 15th World Congress on Health and Biomedical Informatics. Studies in Health Technology and Informatics, vol. 216, IOS Press, pp. 706-710, 15th World Congress on Health and Biomedical Informatics, MEDINFO 2015, Sao Paulo, Brazil, 8/19/15. https://doi.org/10.3233/978-1-61499-564-7-706

Hu Z, Simon GJ , Arsoniadis EG, Wang Y, Kwaan MR, Melton GB. Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data. In Georgiou A, Sarkar IN, de Azevedo Marques PM, editors, MEDINFO 2015: eHealth-Enabled Health - Proceedings of the 15th World Congress on Health and Biomedical Informatics. IOS Press. 2015. p. 706-710. (Studies in Health Technology and Informatics). doi: 10.3233/978-1-61499-564-7-706

Hu, Zhen ; Simon, Gyorgy J. ; Arsoniadis, Elliot G. et al. / Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data. MEDINFO 2015: eHealth-Enabled Health - Proceedings of the 15th World Congress on Health and Biomedical Informatics. editor / Andrew Georgiou ; Indra Neil Sarkar ; Paulo Mazzoncini de Azevedo Marques. IOS Press, 2015. pp. 706-710 (Studies in Health Technology and Informatics).

@inproceedings{77f4b3d0f99f4881ada06f2cdef24e57,

title = "Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data",

abstract = "The National Surgical Quality Improvement Project (NSQIP) is widely recognized as 'the best in the nation' surgical quality improvement resource in the United States. In particular, it rigorously defines postoperative morbidity outcomes, including surgical adverse events occurring within 30 days of surgery. Due to its manual yet expensive construction process, the NSQIP registry is of exceptionally high quality, but its high cost remains a significant bottleneck to NSQIP's wider dissemination. In this work, we propose an automated surgical adverse events detection tool, aimed at accelerating the process of extracting postoperative outcomes from medical charts. As a prototype system, we combined local EHR data with the NSQIP gold standard outcomes and developed machine learned models to retrospectively detect Surgical Site Infections (SSI), a particular family of adverse events that NSQIP extracts. The built models have high specificity (from 0.788 to 0.988) as well as very high negative predictive values (>0.98), reliably eliminating the vast majority of patients without SSI, thereby significantly reducing the NSQIP extractors' burden.",

keywords = "Electronic Health Records, National Surgical Quality Improvement Project, Supervised Learning, Surgical Site Infection",

author = "Zhen Hu and Simon, {Gyorgy J.} and Arsoniadis, {Elliot G.} and Yan Wang and Kwaan, {Mary R.} and Melton, {Genevieve B.}",

note = "Publisher Copyright: {\textcopyright} 2015 IMIA and IOS Press.; 15th World Congress on Health and Biomedical Informatics, MEDINFO 2015 ; Conference date: 19-08-2015 Through 23-08-2015",

year = "2015",

doi = "10.3233/978-1-61499-564-7-706",

language = "English (US)",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "706--710",

editor = "Andrew Georgiou and Sarkar, {Indra Neil} and {de Azevedo Marques}, {Paulo Mazzoncini}",

booktitle = "MEDINFO 2015",

}

TY - GEN

T1 - Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data

AU - Hu, Zhen

AU - Simon, Gyorgy J.

AU - Arsoniadis, Elliot G.

AU - Wang, Yan

AU - Kwaan, Mary R.

AU - Melton, Genevieve B.

PY - 2015

Y1 - 2015

N2 - The National Surgical Quality Improvement Project (NSQIP) is widely recognized as 'the best in the nation' surgical quality improvement resource in the United States. In particular, it rigorously defines postoperative morbidity outcomes, including surgical adverse events occurring within 30 days of surgery. Due to its manual yet expensive construction process, the NSQIP registry is of exceptionally high quality, but its high cost remains a significant bottleneck to NSQIP's wider dissemination. In this work, we propose an automated surgical adverse events detection tool, aimed at accelerating the process of extracting postoperative outcomes from medical charts. As a prototype system, we combined local EHR data with the NSQIP gold standard outcomes and developed machine learned models to retrospectively detect Surgical Site Infections (SSI), a particular family of adverse events that NSQIP extracts. The built models have high specificity (from 0.788 to 0.988) as well as very high negative predictive values (>0.98), reliably eliminating the vast majority of patients without SSI, thereby significantly reducing the NSQIP extractors' burden.

AB - The National Surgical Quality Improvement Project (NSQIP) is widely recognized as 'the best in the nation' surgical quality improvement resource in the United States. In particular, it rigorously defines postoperative morbidity outcomes, including surgical adverse events occurring within 30 days of surgery. Due to its manual yet expensive construction process, the NSQIP registry is of exceptionally high quality, but its high cost remains a significant bottleneck to NSQIP's wider dissemination. In this work, we propose an automated surgical adverse events detection tool, aimed at accelerating the process of extracting postoperative outcomes from medical charts. As a prototype system, we combined local EHR data with the NSQIP gold standard outcomes and developed machine learned models to retrospectively detect Surgical Site Infections (SSI), a particular family of adverse events that NSQIP extracts. The built models have high specificity (from 0.788 to 0.988) as well as very high negative predictive values (>0.98), reliably eliminating the vast majority of patients without SSI, thereby significantly reducing the NSQIP extractors' burden.

KW - Electronic Health Records

KW - National Surgical Quality Improvement Project

KW - Supervised Learning

KW - Surgical Site Infection

UR - http://www.scopus.com/inward/record.url?scp=84951932330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951932330&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-564-7-706

DO - 10.3233/978-1-61499-564-7-706

M3 - Conference contribution

C2 - 26262143

AN - SCOPUS:84951932330

T3 - Studies in Health Technology and Informatics

SP - 706

EP - 710

BT - MEDINFO 2015

A2 - Georgiou, Andrew

A2 - Sarkar, Indra Neil

A2 - de Azevedo Marques, Paulo Mazzoncini

PB - IOS Press

T2 - 15th World Congress on Health and Biomedical Informatics, MEDINFO 2015

Y2 - 19 August 2015 through 23 August 2015

ER -

Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this